A novel hybrid ensemble learning paradigm for nuclear energy consumption forecasting
A novel hybrid ensemble learning paradigm for nuclear energy consumption forecasting
复制标题
一种用于核能消耗预测的新型混合集成学习范式
DOI：
10.1016/j.apenergy.2011.12.030
复制
发表时间：
2012-05
期刊：
影响因子：
11.2
通讯作者：
Wang, Shouyang
中科院分区：
文献类型：
--
作者：
Tang, Ling;Yu, Lean;Wang, Shuai;Li, Jianping;Wang, Shouyang
本文基于“分解与集成”的原理，提出了一种将集成经验模态分解（EEMD）与最小二乘支持向量回归（LSSVR）相结合的新型混合集成学习模式，用于核能消费预测。这种混合集成学习模式是专门为解决核能消耗建模的困难而制定的，核能消耗具有固有的高波动性、复杂性和不规则性。在本文提出的混合集成学习范式中，EEMD作为一种竞争分解方法，首先将核能消耗的原始数据（即较困难的任务）分解为原始数据（即一些相对容易的子任务）的多个独立的内禀模态函数（IMFs）。然后利用LSSVR这一强大的预测工具对提取的所有imf进行独立预测。最后，使用另一个LSSVR将这些预测的imf聚合成一个集合结果作为最终预测。为了说明和验证的目的，提出的学习范式被用于预测中国的核能消费。实证结果表明，混合集成学习范式在水平预测和方向预测方面都优于其他一些流行的预测模型，表明它是预测具有高波动性和不规则性的复杂时间序列的一种很有前途的工具。
In this paper, a novel hybrid ensemble learning paradigm integrating ensemble empirical mode decomposition (EEMD) and least squares support vector regression (LSSVR) is proposed for nuclear energy consumption forecasting, based on the principle of “decomposition and ensemble”. This hybrid ensemble learning paradigm is formulated specifically to address difficulties in modeling nuclear energy consumption, which has inherently high volatility, complexity and irregularity. In the proposed hybrid ensemble learning paradigm, EEMD, as a competitive decomposition method, is first applied to decompose original data of nuclear energy consumption (i.e. a difficult task) into a number of independent intrinsic mode functions (IMFs) of original data (i.e. some relatively easy subtasks). Then LSSVR, as a powerful forecasting tool, is implemented to predict all extracted IMFs independently. Finally, these predicted IMFs are aggregated into an ensemble result as final prediction, using another LSSVR. For illustration and verification purposes, the proposed learning paradigm is used to predict nuclear energy consumption in China. Empirical results demonstrate that the novel hybrid ensemble learning paradigm can outperform some other popular forecasting models in both level prediction and directional forecasting, indicating that it is a promising tool to predict complex time series with high volatility and irregularity.
登录
查看更多内容
影响因子：
9
作者：
Yi-chong Xu
通讯作者：
Yi-chong Xu
影响因子：
9
作者：
J. Jewell
通讯作者：
J. Jewell
影响因子：
2.7
作者：
Qiang Yan;Anjian Wang;Gaoshang Wang;Wenjia Yu;Qishen Chen
通讯作者：
Qiang Yan;Anjian Wang;Gaoshang Wang;Wenjia Yu;Qishen Chen
影响因子：
9
作者：
H. Pao
通讯作者：
H. Pao
影响因子：
11.2
作者：
Bianco, Vincenzo;Manca, Oronzio;Minea, Alina A.
通讯作者：
Minea, Alina A.